CN116597016A - Optical fiber endoscope image calibration method - Google Patents
Optical fiber endoscope image calibration method Download PDFInfo
- Publication number
- CN116597016A CN116597016A CN202310516632.2A CN202310516632A CN116597016A CN 116597016 A CN116597016 A CN 116597016A CN 202310516632 A CN202310516632 A CN 202310516632A CN 116597016 A CN116597016 A CN 116597016A
- Authority
- CN
- China
- Prior art keywords
- image
- calibration plate
- function
- calibration
- extracting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 239000013307 optical fiber Substances 0.000 title claims abstract description 26
- 238000001914 filtration Methods 0.000 claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 239000000835 fiber Substances 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims abstract description 4
- 238000012216 screening Methods 0.000 claims abstract description 3
- 239000003550 marker Substances 0.000 claims description 9
- 101150064138 MAP1 gene Proteins 0.000 claims description 3
- 101100075995 Schizosaccharomyces pombe (strain 972 / ATCC 24843) fma2 gene Proteins 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 2
- 238000006073 displacement reaction Methods 0.000 abstract description 33
- 238000012360 testing method Methods 0.000 abstract description 11
- 238000005259 measurement Methods 0.000 abstract description 4
- 238000003672 processing method Methods 0.000 abstract description 2
- 230000011218 segmentation Effects 0.000 abstract description 2
- 238000012937 correction Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 230000000379 polymerizing effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10068—Endoscopic image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a fiber endoscope image calibration method, which comprises the steps of carrying out Gaussian filtering on a calibration plate image; filtering black background and honeycomb grid in the image processed in the previous step through binarization, eliminating useless information in the image, and extracting the characteristics of the outline and the marking points of the calibration plate; identifying and extracting a plurality of mark points in the image of the calibration plate, screening the mark points in the calibration plate, extracting a mark point area, and then obtaining the center coordinates of the mark points by using a center-of-gravity calculation mode; and correcting the optical fiber endoscope image by adopting a dot matrix template calibration method according to the extracted central coordinate array of the marking points. The method has strong robustness, and the calibration method has better robustness on the identification of the mark points of the calibration plate under different distances, different angles and mixed multiple noise interferences; the precision is high, the measurement error is not more than 10 mu m by using the image displacement non-contact test system of the calibration method, and the error can reach a plurality of mu m by using processing methods such as sub-pixels, segmentation and the like.
Description
Technical Field
The invention relates to the technical field of image calibration, in particular to an optical fiber endoscope image calibration method.
Background
The optical fiber endoscope is widely applied to probing of cracks, corrosion and other conditions in a narrow space with a complex structure due to the characteristics of small diameter, bendable probe and the like. During exploration, the optical fiber endoscope is stretched into the object to be detected, a high-resolution digital camera is arranged at the eyepiece end of the endoscope, images in the optical fiber endoscope are shot and stored, and the acquired images are analyzed in real time by software.
However, the images acquired by the camera through the optical fiber endoscope are affected by the external environment and defects of the camera, noise is generated, the degradation of the images is caused, compared with the images shot by the conventional lens, phenomena of obviously reduced contrast, blurred image quality, indistinguishable background and target objects and the like are generated, and the subsequent analysis is difficult; FIG. 1 is a conventional lens calibration plate image; FIG. 2 shows an image of a fiber optic lens calibration plate; meanwhile, due to the inherent characteristics of the optical fiber lens, in order to make the shot target surface as large as possible, the objective lens of the light endoscope adopts the design principles of small aperture, large field of view and large depth of field, so that about 30% barrel-shaped distortion exists in the image acquired by the camera at the eyepiece, and in order to accurately extract the central coordinate of the mark point, distortion correction is needed to be carried out on the image.
Based on the two reasons, the conventional image calibration calculation method is difficult to be applied to the optical fiber endoscope image, and can bring larger error to analysis.
A fiber optic endoscope image calibration method was developed to solve the above-mentioned problems.
Disclosure of Invention
The invention aims to solve the problems and designs an optical fiber endoscope image calibration method.
The invention realizes the above purpose through the following technical scheme:
the optical fiber endoscope image calibration method comprises the following steps:
s1, gaussian filtering is carried out on a calibration plate image shot by a camera through an optical fiber mirror;
s2, filtering black background and honeycomb grids in the image processed in the step S1 through a binarization method, eliminating useless information in the image, and extracting the characteristics of the outline and the marking points of the calibration plate;
s3, identifying and extracting a plurality of marking points in the image of the calibration plate processed in the step S2, screening the marking points in the calibration plate, extracting marking point areas, and obtaining central coordinates of the marking points by using a gravity center calculation mode;
and S4, correcting the optical fiber endoscope image by adopting a dot matrix template calibration method according to the central coordinate array of the mark points extracted in the third step.
Specifically, in step S1, the image is gaussian filtered with a gauss_filter () function according to the noise type of the honeycomb mesh in the calibration plate image.
Specifically, in step S2, a binarization method of the local threshold is used to extract features of the calibration plate profile and the marker points.
Further, in step S2, a local_threshold () function is applied to perform a local threshold binarization operation on the gaussian filtered image, which specifically includes:
s21, setting the size of a mask by adjusting the value of mask_size in a local_threshold () function;
s22, further extracting the details of the mark points by setting the maximum assumed value of range in the local_threshold () function;
s23, filling the area by using a fill_up () function, filling the calibration plate into a square, then passing through a select_shape () function, extracting the rectangular area of the calibration plate according to the actual length and width parameters of the calibration plate, and then performing twice subtraction on the extracted rectangular area of the calibration plate and the original area by using a difference () function, and extracting the outline and the mark points of the calibration plate;
s24, after the outline and the mark point of the calibration plate are extracted, a blank image with the same size as the original image is generated by using a gen_image_const () function, the extracted outline and mark point of the calibration plate are printed into a new image by using a paint_region () function, so that the outline and the mark point of the calibration plate are extracted, and the honeycomb grid is filtered.
As one preferable, in step S21, mask_size is set to be larger than the equivalent diameter of the mark point to be divided and to be an odd number.
As another preference, in step S21, the mask_size is even, and the next larger odd value is used by default.
Preferably, in step S22, the gray value range of the image is acquired with the min_max_gray () function, and range is within 0.5 times of gray range.
Specifically, in step S4, the distortion coefficient of the image is obtained through the calibrate Camera () function, then the readParam () function is used to read the distortion coefficient, when the function parameter alpha is 1, the field of view is unchanged and smaller than 1, the field of view is required to be scaled, then the initUndicator electifymap () function is used to output two parameters, namely map1 and map2, according to the distortion coefficient, and finally the remap () function is used to obtain the corrected image.
The invention has the beneficial effects that:
1. the calibration method is high in universality, and the calibration method can correct and identify images shot by optical fiber endoscopes with different diameters and different pixels;
2. the robustness is strong, and the calibration method has better robustness for identifying the mark points of the calibration plate under different distances, different angles and mixed multiple noise interferences;
3. the precision is high, the measurement error is not more than 10 mu m by using the image displacement non-contact test system of the calibration method, and the error can reach a plurality of mu m by using processing methods such as sub-pixels, segmentation and the like.
Drawings
FIG. 1 is a conventional lens calibration plate image;
FIG. 2 is an image of a fiber lens calibration plate;
FIG. 3-1 is a calibration plate image before Gaussian filtering;
FIG. 3-2 is a Gaussian filtered calibration plate image;
FIG. 4 is an image of a calibration plate binarized by an automatic threshold;
FIG. 5 is a partial thresholded calibration plate image;
FIG. 6 is a calibration plate image processed with different mask_size values in the local_threshold () function; where a is mask_size=15; b is mask_size=31;
FIG. 7 is a calibration plate image processed with different range max hypothesis values in the local_threshold () function; wherein a is range=92.5; b is range=20.5;
FIG. 8 is a calibration plate image after being processed by a fill_up () function;
FIG. 9 is a calibration plate image after being processed by the select_shape () function;
FIG. 10 is a calibration plate image after a first process by a difference () function;
FIG. 11 is a calibration plate image after a second treatment with a difference () function;
FIG. 12 is a calibration plate image after being processed by the paint_region () function;
fig. 13 is a graph of the effect comparison of the processing of different Minarea parameter values in the findCirclesGrid () function, where a is minarea=300; b is minarea=100;
FIG. 14 is a calibration plate image showing the success of marker point identification and extraction;
FIG. 15 is a corrected calibration plate image;
FIG. 16 is a schematic drawing of marker image area extraction;
FIG. 17 is a schematic diagram of a comparison of displacement data of a laser displacement meter and an image displacement testing system;
FIG. 18 shows calibration correction results for a calibration plate 1cm from the lens and parallel to the lens; wherein a is an original picture; b is a calibration correction result schematic diagram;
FIG. 19 is a calibration correction result for a calibration plate 3cm from the lens and parallel to the lens; wherein a is an original picture; b is a calibration correction result schematic diagram;
FIG. 20 is a calibration correction result of the calibration plate 0.5cm from the lens, at 15 degrees to the lens and with more noise disturbance; wherein a is an original picture; and b is a schematic diagram of calibration and correction results.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the present invention, it should be understood that the directions or positional relationships indicated by the terms "upper", "lower", "inner", "outer", "left", "right", etc. are based on the directions or positional relationships shown in the drawings, or the directions or positional relationships conventionally put in place when the inventive product is used, or the directions or positional relationships conventionally understood by those skilled in the art are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific direction, be configured and operated in a specific direction, and therefore should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like, are used merely to distinguish between descriptions and should not be construed as indicating or implying relative importance.
In the description of the present invention, it should also be noted that, unless explicitly specified and limited otherwise, terms such as "disposed," "connected," and the like are to be construed broadly, and for example, "connected" may be either fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
The following describes specific embodiments of the present invention in detail with reference to the drawings.
As shown in fig. 1, a method for calibrating an image of a fiber optic endoscope includes the following steps:
s1, gaussian filtering is carried out on a calibration plate image shot by a camera through an optical fiber mirror; the optical fiber lens is formed by winding and polymerizing innumerable optical fiber bundles, and an image shot by the camera through the optical fiber mirror can show a honeycomb grid shape and interfere with the identification of the marking points, so that the honeycomb grid in the image needs to be filtered. Performing Gaussian filtering on the image by using a Gaussian_filter_threshold () function according to the noise type of the honeycomb grid, wherein the filtering effect is shown in figures 3-1 and 3-2, and figure 3-1 is a calibration plate image before Gaussian filtering; FIG. 3-2 is a Gaussian filtered calibration plate image;
s2, filtering black background and honeycomb grids in the image processed in the step S1 through a binarization method, eliminating useless information in the image, enhancing the detectability of the information of interest, and providing reliable guarantee for separation of mark points and backgrounds on the calibration plate; extracting the characteristics of the outline of the calibration plate and the marking points by adopting a binarization method of a local threshold value;
the conventional binarization method includes two methods, namely an automatic threshold value and a local threshold value, and the automatic threshold value binarization auto_threshold () function can display details of the calibration plate and the marking points, but cannot extract the effective features of the marking points and the outline of the calibration plate, as shown in fig. 4. Therefore, the feature of the calibration plate outline and the marking point is extracted by adopting a local threshold binarization method, namely, a local_threshold () function is used to perform local threshold binarization operation on the Gaussian filtered image, as shown in fig. 5. The binarization operation of the local threshold on the Gaussian filtered image by using the local_threshold () function specifically comprises:
s21, setting a mask size by adjusting mask_size in a local_threshold () function; i.e. the size of the neighborhood in the local thresholding method. The smaller the mask_size value, the finer the mark point split, so the mask_size must be set to be larger than the equivalent diameter of the mark point to be split, typically odd, and if mask_size is even, the next larger odd value is used by default. As shown in fig. 6, a calibration plate image is processed with mask_size values in different local_threshold () functions; where a is mask_size=15; b is mask_size=31;
s22, further extracting the details of the mark points by setting the maximum assumed value of range in the local_threshold () function; the range of gray values of the image is obtained by using a min_max_gray () function, the range is within 0.5 times of GrayRange, the larger the range value is, the finer the extracted point is, the smaller the range value is, and the thicker the point is. Range=gray range/range dev is taken according to the empirical range value, wherein range dev is a coefficient, and the value is 9. As shown in fig. 7, the calibration plate image is shown under different range values; wherein a is range=92.5; b is range=20.5;
s23, filling the area by using a fill_up () function, and filling the calibration plate into a square shape, as shown in FIG. 8; then, through the select_shape () function, extracting the rectangular area of the calibration plate according to the actual length and width parameters of the calibration plate, as shown in fig. 9; then, through a difference () function, performing two subtractions on the extracted rectangular area and the original area of the calibration plate, and extracting the outline and the mark points of the calibration plate, wherein the two treatments are respectively shown in fig. 10 and 11; the calibration plate image is subjected to fill_up () processing;
s24, after the outline and the mark point of the calibration plate are extracted, a blank image with the same size as the original image is generated by using a gen_image_const () function, the extracted outline and mark point of the calibration plate are printed into a new image by using a paint_region () function, so that the outline and the mark point of the calibration plate are successfully extracted, and the honeycomb grid is filtered, as shown in fig. 12.
S3, identifying and extracting 49 mark points in the calibration plate image processed in the step S2 by using a findCirclesgrid () function, extracting a mark point region, and then obtaining a mark point center coordinate by using a center-of-gravity calculation mode; the extraction application is shown in fig. 13.
When the minimum area parameter Minarea is inappropriate, the central coordinates of the marking points of the calibration plate cannot be extracted correctly; the marking points of the calibration plate can be correctly identified and arranged according to a certain sequence only when proper minimum area parameters are set according to the pixel area occupied by the marking points. Fig. 14 shows the calibration plate image obtained after successful identification of the mark points.
And S4, correcting the optical fiber endoscope image by adopting a dot matrix template calibration method according to the central coordinate array of the mark points extracted in the third step.
Firstly, obtaining distortion coefficients of an image through a calicate Camera () function, then using a ReadParam () function to read the distortion coefficients, when a function parameter alpha is 1, the field of view is unchanged and is required to be scaled when the function parameter alpha is smaller than 1, then using an initUndicator transform map () function to output two parameters of map1 and map2 according to the distortion coefficients, and finally using a remap () function to obtain a corrected image; the calibration method can eliminate barrel distortion by about 95%, the error is 1 pixel, and the actual error is about 5 μm according to the calibration relation and the adopted sub-pixel calculation method, and the corrected image is shown in fig. 15.
Generally, the mark point area only occupies a small part of the whole picture, so that an image region of interest (ROI) can be set to frame the required mark points, and only the image in the ROI is processed and calculated. After the interesting area is manually drawn in the image by using the draw_rectangle1 () function, a rectangular area is generated by using the gen_rectangle1 () function, and finally the interesting image is obtained by using the reduce_domain () function.
After the region extraction is carried out to obtain the interested image, the abscissa and the ordinate of the region mark point are identified, and the displacement change is obtained. And manufacturing micro-displacement by using a precision displacement platform, analyzing and calculating centroid coordinates of mark points before and after displacement change, and obtaining a corresponding relation between pixels and displacement according to known displacement values. Then, a laser displacement meter and an image displacement testing system are adopted to carry out comparison verification on a precision displacement platform, and the verification method comprises the following steps: the method comprises the steps of collecting marker point images through an optical fiber endoscope, designing the shapes and the layout of the marker points as shown in fig. 16, wherein the equivalent diameters of the marker points are 0.5mm, the transverse spacing is 1mm, the longitudinal spacing is 2mm, pasting back glue, calculating and analyzing the collected marker point images by using the calibration method, and comparing displacement values obtained by an image displacement testing system with values measured by a laser displacement meter.
The measurement error of the laser displacement meter is 1 μm, the data are shown in table 1 (correspondingly, as shown in fig. 17, the displacement data of the laser displacement meter and the image displacement test system are compared and schematic), wherein T represents time, the micro-displacement D1-D8 is produced by using the displacement platform for manufacturing, C represents the centroid coordinate variation value of the mark point under the pixel coordinate system, D represents the average pixel corresponding displacement value, JD represents the data measured by the laser displacement meter, and TD represents the image displacement test system data. According to the calibration relation and the adopted sub-pixel calculation method, the data in the table can be analyzed to obtain that the corresponding displacement of 1 pixel is about 10 mu m, the measurement data of the laser displacement meter and the data of the image displacement test system are basically overlapped, the maximum difference value is 2.4 mu m, the image calibration method and the image displacement test system are proved to be feasible, and the test result is true and reliable.
Table 1 displacement data of laser displacement meter and image displacement test system
Calibrating and correcting different types of calibration plate images shot by the optical fiber endoscope by using a designed calibration system, wherein fig. 18 is a calibration and correction result of the calibration plate being 1cm away from the lens and being parallel to the lens; FIG. 19 is a calibration correction result for a calibration plate 3cm from the lens and parallel to the lens; FIG. 20 shows calibration correction results with the calibration plate at an angle to the lens of 0.5cm from the lens and with more noise interference.
As can be seen from the legend, the calibration method is high in universality and robustness and suitable for correction and identification of images with different quality under various scenes.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that it will be apparent to those skilled in the art that several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the scope of the invention.
Claims (8)
1. The optical fiber endoscope image calibration method is characterized by comprising the following steps of:
s1, gaussian filtering is carried out on a calibration plate image shot by a camera through an optical fiber mirror;
s2, filtering black background and honeycomb grids in the image processed in the step S1 through a binarization method, eliminating useless information in the image, and extracting the characteristics of the outline and the marking points of the calibration plate;
s3, identifying and extracting a plurality of marking points in the image of the calibration plate processed in the step S2, screening the marking points in the calibration plate, extracting marking point areas, and obtaining central coordinates of the marking points by using a gravity center calculation mode;
and S4, correcting the optical fiber endoscope image by adopting a dot matrix template calibration method according to the central coordinate array of the mark points extracted in the third step.
2. A method of calibrating a fiber optic endoscope image according to claim 1 and wherein in step S1, the image is gaussian filtered with a gauss_filter () function according to the noise type of the honeycomb grid in the calibration plate image.
3. The method according to claim 1, wherein in step S2, a local threshold binarization method is used to extract features of the calibration plate profile and the marker points.
4. A method for calibrating an image of a fiber optic endoscope according to claim 3 and wherein in step S2, a local_threshold () function is applied to perform a local thresholding binarization operation on the gaussian filtered image, specifically comprising:
s21, setting the size of a mask by adjusting the value of mask_size in a local_threshold () function;
s22, further extracting the details of the mark points by setting the maximum assumed value of range in the local_threshold () function;
s23, filling the area by using a fill_up () function, filling the calibration plate into a square, then passing through a select_shape () function, extracting the rectangular area of the calibration plate according to the actual length and width parameters of the calibration plate, and then performing twice subtraction on the extracted rectangular area of the calibration plate and the original area by using a difference () function, and extracting the outline and the mark points of the calibration plate;
s24, after the outline and the mark point of the calibration plate are extracted, a blank image with the same size as the original image is generated by using a gen_image_const () function, the extracted outline and mark point of the calibration plate are printed into a new image by using a paint_region () function, so that the outline and the mark point of the calibration plate are extracted, and the honeycomb grid is filtered.
5. The method according to claim 4, wherein in step S21, mask_size is set to be larger than the equivalent diameter of the marker point to be segmented and to be an odd number.
6. The method according to claim 4, wherein in step S21, the mask_size is even, and the next larger odd value is used by default.
7. The method according to claim 4, wherein in step S22, a gray value range of the image is obtained by using a min_max_gray () function, and range is within 0.5 times of gray range.
8. The method for calibrating an optical fiber endoscope image according to claim 1, wherein in step S4, a distortion coefficient of the image is obtained through a calibration Camera () function, then the distortion coefficient is read by using a ReadParam function, when a function parameter alpha is 1, a field of view is unchanged and is smaller than 1, the field of view is required to be scaled, then two parameters of map1 and map2 are obtained by using an initUndicatrifyifigmap () function according to the distortion coefficient output, and finally a corrected image is obtained by using a remap () function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310516632.2A CN116597016A (en) | 2023-05-09 | 2023-05-09 | Optical fiber endoscope image calibration method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310516632.2A CN116597016A (en) | 2023-05-09 | 2023-05-09 | Optical fiber endoscope image calibration method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116597016A true CN116597016A (en) | 2023-08-15 |
Family
ID=87592997
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310516632.2A Pending CN116597016A (en) | 2023-05-09 | 2023-05-09 | Optical fiber endoscope image calibration method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116597016A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117710250A (en) * | 2024-02-04 | 2024-03-15 | 江苏无右微创医疗科技有限公司 | Method for eliminating honeycomb structure imaged by fiberscope |
-
2023
- 2023-05-09 CN CN202310516632.2A patent/CN116597016A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117710250A (en) * | 2024-02-04 | 2024-03-15 | 江苏无右微创医疗科技有限公司 | Method for eliminating honeycomb structure imaged by fiberscope |
| CN117710250B (en) * | 2024-02-04 | 2024-04-30 | 江苏无右微创医疗科技有限公司 | Method for eliminating honeycomb structure imaged by fiberscope |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110866924B (en) | Line structured light center line extraction method and storage medium | |
| CN110706224B (en) | Optical element weak scratch detection method, system and device based on dark field image | |
| CN111260615B (en) | Laser and machine vision fusion-based method for detecting apparent diseases of unmanned aerial vehicle bridge | |
| CN115170669B (en) | Identification and positioning method and system based on edge feature point set registration and storage medium | |
| CN112686920A (en) | Visual measurement method and system for geometric dimension parameters of circular part | |
| CN115880373B (en) | Calibration plate and calibration method of stereoscopic vision system based on novel coding features | |
| CN113034474A (en) | Test method for wafer map of OLED display | |
| CN116597016A (en) | Optical fiber endoscope image calibration method | |
| CN114565552A (en) | Method and device for detecting surface defects of optical element and electronic equipment | |
| CN111354047A (en) | Camera module positioning method and system based on computer vision | |
| CN110705553B (en) | Scratch detection method suitable for vehicle distant view image | |
| CN112836726B (en) | Pointer instrument indication reading method and device based on video information | |
| CN113112396B (en) | Method for detecting conductive particles | |
| CN114612412A (en) | Processing method of three-dimensional point cloud data, application of processing method, electronic device and storage medium | |
| CN116563298B (en) | Cross line center sub-pixel detection method based on Gaussian fitting | |
| CN116977316A (en) | Full-field detection and quantitative evaluation method for damage defects of complex-shape component | |
| CN113554688B (en) | O-shaped sealing ring size measurement method based on monocular vision | |
| CN116125489A (en) | Indoor object three-dimensional detection method, computer equipment and storage medium | |
| CN114926417B (en) | Microscopic imaging detection method and system for weak scratches on surface of high-density flexible FPC | |
| CN115760860A (en) | Multi-type workpiece dimension visual measurement method based on DXF file import | |
| CN113012121B (en) | Method and device for processing bare chip scanning result, electronic equipment and storage medium | |
| CN114387232A (en) | Wafer center positioning, wafer gap positioning and wafer positioning calibration method | |
| CN114821035A (en) | Distance parameter identification method for infrared temperature measurement equipment of power equipment | |
| CN110660073B (en) | Straight line edge recognition equipment | |
| CN117115488B (en) | Water meter detection method based on image processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |